modelbenchmark.io

Voxtral Small

Mistral · voxtral-small

Compare

Instruct model with native audio input for speech understanding and tool use

Specification

mistral listing

Context
33K
Max output
32K
Released
2025-07-15
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, audio, pdf
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.10
Output
$0.40
Cache read
$0.01

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.10$0.40$0.01—33K
32K
33K
—
edenai$0.10$0.40$0.01—33K32K—
llmtr$0.10$0.30——32K32K—
tempr$0.10$0.40——32K32K—
cortecs$0.123$0.368$0.012—32K32K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02cortecsCache read$0.011
2026-09-15cortecsCache read$0.012
2026-09-02cortecsInput$0.111
2026-09-15cortecsInput$0.123
2026-09-02cortecsOutput$0.334
2026-09-15cortecsOutput$0.368
2026-09-02mistralOutput$0.30
2026-10-08mistralOutput$0.40
2026-10-21mistralOutput$0.40
2026-09-24temprOutput$0.30
2026-10-22temprOutput$0.40

More from Mistral

most-hosted first